Pith. sign in

REVIEW 10 cited by

CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.12644 v3 pith:RBVDWFGD submitted 2024-11-19 cs.SE cs.AI

Ye Liu , Rui Meng , Shafiq Joty , Silvio Savarese , Caiming Xiong , Yingbo Zhou , Semih Yavuz This is my paper · ORCID
classification cs.SEcs.AI
keywords retrievalcodemodelperformancetasksmodelstextacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite the success of text retrieval in many NLP tasks, code retrieval remains a largely underexplored area. Most text retrieval systems are tailored for natural language queries, often neglecting the specific challenges of retrieving code. This gap leaves existing models unable to effectively capture the diversity of programming languages and tasks across different domains, highlighting the need for more focused research in code retrieval. To address this, we introduce CodeXEmbed, a family of large-scale code embedding models ranging from 400M to 7B parameters. Our novel training pipeline unifies multiple programming languages and transforms various code-related tasks into a common retrieval framework, enhancing model generalizability and retrieval performance. Our 7B model sets a new state-of-the-art (SOTA) in code retrieval, outperforming the previous leading model, Voyage-Code, by over 20% on CoIR benchmark. In addition to excelling in code retrieval, our models demonstrate competitive performance on the widely adopted BeIR text retrieval benchmark, offering versatility across domains. Experimental results demonstrate that improving retrieval performance significantly enhances end-to-end Retrieval-Augmented Generation (RAG) performance for code-related tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization

    cs.SE 2026-07 conditional novelty 7.0 of 10

    MM-IssueLoc is a controlled multimodal repository-level issue-localization benchmark showing current systems achieve at most 38.96% file Acc@5 and that visual evidence helps only unevenly.

  2. Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Schema retrieval can be benchmarked as retrieval, and corpus-adaptive fine-tuning lifts a 305M embedder to 75.6 recall@10, rivaling 4–8B models.

  3. CASP: An evaluation dataset for formal verification of C code

    cs.FL 2025-08 conditional novelty 6.0 of 10

    CASP is the largest openly released dataset of 506 Frama-C-verified C code and ACSL specification pairs, designed for benchmarking LLMs on formal verification.

  4. Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding

    cs.LG 2025-08 conditional novelty 6.0 of 10

    LRTab retrieves error-avoiding prompt conditions learned from incorrect chain-of-thought traces on training tables to improve LLM tabular reasoning, achieving modest gains on WikiTQ and TabFact.

  5. Exploiting Leaderboards for Large-Scale Distribution of Malicious Models

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A new attack framework, TrojanClimb, shows that adversaries can place models with embedded backdoors or biases on public leaderboards while retaining competitive rankings, across text embeddings, text generation, spee...

  6. Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

    cs.SE 2025-06 conditional novelty 6.0 of 10

    Across ten software engineering tasks and four LLMs, no prompting technique wins consistently; ES-KNN is best on many tasks, some techniques underperform the baseline, and USC is best for code QA and code generation.

  7. CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs

    cs.SE 2025-05 conditional novelty 6.0 of 10

    CodeMirage is a ten-language, ten-LLM benchmark with original and paraphrased AI code, and it shows current AI-generated-code detectors drop sharply under cross-model and low-false-alarm settings.

  8. The "I Don't Know" Filter: Enhancing Agentic Reliability in Function Calling

    cs.SE 2026-07 conditional novelty 5.5 of 10

    A multi-sample uncertainty classifier filter improves agent reliability (IDKS) by abstaining on uncertain function calls across open SLMs and BFCL-style benchmarks.

  9. ParaStudent: Generating and Evaluating Realistic Student Code by Teaching LLMs to Struggle

    cs.CY 2025-07 conditional novelty 5.0 of 10

    Fine-tuning a 7B code model on real student submissions produces code that better matches student error patterns, style, and incremental revision trajectories than prompting-only models across two temporal resolutions.

  10. CIDRe: A Reference-Free Multi-Aspect Criterion for Code Comment Quality Measurement

    cs.SE 2025-05 reject novelty 5.0 of 10

    CIDRe is a reference-free, four-part quality score for structured code comments, validated on 840 manually labeled Russian comments and reported to improve comment generation after dataset filtering.

Pith tools